📌Overview

Purpose: To provide a Model Context Protocol (MCP) server implementation for effective interaction with Elasticsearch, enhancing document search, index analysis, and cluster management.

Overview: The Elasticsearch MCP Server serves as a bridge for users to interact seamlessly with Elasticsearch, facilitating operations like searching for documents, retrieving index configurations, and monitoring cluster health through a variety of easy-to-use tools.

Key Features:

Index Operations: Includes functions like list_indices, get_mapping, and get_settings that enable users to manage and retrieve information about indices in the Elasticsearch cluster.
Document Operations: The search_documents feature allows users to execute complex searches within an index using Elasticsearch’s Query DSL, streamlining data retrieval tasks.
Cluster Operations: Functions such as get_cluster_health and get_cluster_stats provide valuable insights into the overall status and statistics of the Elasticsearch cluster, helping maintain optimal performance.

Elasticsearch MCP Server

Overview

Elasticsearch MCP Server is a Model Context Protocol (MCP) server implementation that enables interaction with Elasticsearch. It allows users to search documents, analyze indices, and manage clusters through various tools.

Demo

For a demonstration, visit: Demo Link

Features

Index Operations

list_indices: List all indices in the Elasticsearch cluster.
get_mapping: Retrieve the mapping configuration for a specific index.
get_settings: Get the settings configuration for a specific index.

Document Operations

search_documents: Search documents in an index using Elasticsearch Query DSL.

Cluster Operations

get_cluster_health: Get health status of the cluster.
get_cluster_stats: Get statistical information about the cluster.

Start Elasticsearch Cluster

You can start the Elasticsearch cluster using Docker Compose:

docker-compose up -d

This command will initiate a 3-node Elasticsearch cluster along with Kibana. The default credentials are:

Username: elastic
Password: test123

You can access Kibana at http://localhost:5601.

Usage with Claude Desktop

Option 1: Installing via Smithery

To automatically install the Elasticsearch Server for Claude Desktop using Smithery, run:

npx -y @smithery/cli install elasticsearch-mcp-server --client claude

Option 2: Using `uvx`

To install the package using uvx, add the following configuration to Claude Desktop's config file claude_desktop_config.json:

{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "uvx",
      "args": [
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTIC_HOST": "https://localhost:9200",
        "ELASTIC_USERNAME": "elastic",
        "ELASTIC_PASSWORD": "test123"
      }
    }
  }
}

Option 3: Using `uv` for local development

To use uv, clone the repository and specify the local path in the claude_desktop_config.json:

{
  "mcpServers": {
    "elasticsearch": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/src/elasticsearch_mcp_server",
        "run",
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTIC_HOST": "https://localhost:9200",
        "ELASTIC_USERNAME": "elastic",
        "ELASTIC_PASSWORD": "test123"
      }
    }
  }
}

Configuration file locations:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

After editing the config, restart Claude Desktop to load the new MCP server. You can then interact with your Elasticsearch cluster using natural language commands, such as:

"List all indices in the cluster"
"How old is the student Bob?"
"Show me the cluster health status"

License

This project is licensed under the Apache License Version 2.0 - see the LICENSE file for details.

elasticsearch-mcp-server